skill

browser-agent

[browser-agent] Never send a human to do a machine's job.

PaulClawX/browser-agentcommunitylistedunreviewed

Set up

Skills are installed by placing their folder where your agent loads skills.

Download ZIP from GitHub Open the repository

The download comes from github.com/PaulClawX/browser-agent itself, not from our server, so what you get is exactly what its author published.

Install instructions come from the README

Skills do not use an MCP config. Follow the steps in the README below.

README

synced Oct 25, 2026

Browser Agent

Quick Navigation

[!TIP] I'm a human -> Read this README for install, setup, and safe workflows.

I'm an agent -> Read SKILL.md for operation rules and execution patterns. (Recommended)

browser-agent is a minimal runtime that lets agents control your real Chrome session directly over CDP, while keeping task logic editable in-repo.

For operators: one command surface for browser actions, diagnostics, and updates.
For agents: stable helper APIs (new_tab, js, click_at_xy, upload_file, raw cdp).
For reliability: interaction skills and domain skills to encode repeatable mechanics.

Quick Start

For Agent (Recommended)

Tell your coding agent:

Install Browser Agent from https://github.com/PaulClawX/browser-agent and set it up to control my Chrome

For Human

git clone https://github.com/PaulClawX/browser-agent && cd browser-agent && uv tool install -e . && browser-agent --doctor

Browser Connection

Attach to your normal Chrome profile

Open chrome://inspect/#remote-debugging
Enable Allow remote debugging for this browser instance
Accept the Chrome allow popup when prompted

Re-run:

browser-agent -c 'print(page_info())'

See install.md for full setup.

Workflows

Tier	Workflow	Expected Behavior
Stable	General browser automation	Deterministic tab + DOM + input operations through CDP helpers
Stable	Upload-driven tasks	Upload confirmation before submit; fail-fast if upload isn't verifiable
Stable	Gemini image generation/editing	Prompt + reference flow with strict upload-first gating and export
Stable	Diagnostics and lifecycle	`--doctor`, daemon auto-start, update checks
Best-effort	Complex anti-bot sites	Fallback to coordinate actions, retries, and skill-specific patterns

Project Layout

src/browser_harness/ - core runtime modules
SKILL.md - operator rules for day-to-day use
install.md - first-time install and connection
docs/interaction-skills/ - reusable browser mechanics playbooks
src/agent-workspace/agent_helpers.py - task-specific helper extensions
docs/domain-skills/ - site-specific playbooks

Core Contributors and Maintainers

📧 Contact

Feel free to open an issue if you have any questions or suggestions. If this project helps you, please give it a ⭐ Star!

Acknowledgements

This project builds on and is inspired by the following open-source work:

browser-use/browser-harness - the primary code and architecture source.
OpenClaudex/openreview-agent - OpenReview dry-run workflow inspiration.